Amber: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1133 ± 31, rank #10255 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 73.79 | Normalized accuracy (%) (10-shot) | 24 |
| Open LLM Leaderboard v1 - WinoGrande | 67.88 | Accuracy (%) (5-shot) | 21.8 |
| Open LLM Leaderboard v1 - GSM8K | 2.81 | Accuracy (%) (5-shot) | 20.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 40.96 | Normalized accuracy (%) (25-shot) | 17.3 |
| Open LLM Leaderboard v1 - MMLU | 26.84 | Accuracy (%) (5-shot) | 13.9 |
| URIAL-Bench - Humanities | 2.1 | Judge Score (0-10) | 5.6 |
| URIAL-Bench - Reasoning | 1.4 | Judge Score (0-10) | 5.6 |
| URIAL-Bench - Turn 2 | 1.32 | Judge Score (0-10) | 5.6 |
| URIAL-Bench - Writing | 1.5 | Judge Score (0-10) | 5.6 |
| URIAL-Bench - Coding | 1 | Judge Score (0-10) | 2.8 |
| URIAL-Bench - Math | 1 | Judge Score (0-10) | 2.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 33.56 | MC2 (%) (0-shot) | 0.7 |
Interactive version: theaggregate.ai/model?slug=amber · How It Works · Data refreshed daily, snapshot 2026-11-08.